# Learning to Regress Bodies from Images using Differentiable Semantic Rendering

arXiv: https://arxiv.org/abs/2110.03480 · HTML: https://mlsanity.com/paper/2110.03480/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 55 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 30 of 37)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Stacked Hourglass Networks for Human Pose Estimation](https://mlsanity.com/paper/1603.06937/) (2016)
- [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017)
- [PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization](https://mlsanity.com/paper/1905.05172/) (2019)
- [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016)
- [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019)
- [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019)
- [DensePose: Dense Human Pose Estimation In The Wild](https://mlsanity.com/paper/1802.00434/) (2018)
- [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020)
- [Simple Baselines for Human Pose Estimation and Tracking](https://mlsanity.com/paper/1804.06208/) (2018)
- [Monocular 3D Human Pose Estimation In The Wild Using Improved CNN Supervision](https://mlsanity.com/paper/1611.09813/) (2016)
- [Soft Rasterizer: A Differentiable Renderer for Image-based 3D Reasoning](https://mlsanity.com/paper/1904.01786/) (2019)
- [A simple yet effective baseline for 3d human pose estimation](https://mlsanity.com/paper/1705.03098/) (2017)
- [Learning 3D Human Dynamics from Video](https://mlsanity.com/paper/1812.01601/) (2018)
- [Convolutional Mesh Regression for Single-Image Human Shape Reconstruction](https://mlsanity.com/paper/1905.03244/) (2019)
- [Learning to Estimate 3D Human Pose and Shape from a Single Color Image](https://mlsanity.com/paper/1805.04092/) (2018)
- [Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose](https://mlsanity.com/paper/1611.07828/) (2016)
- [Unite the People: Closing the Loop Between 3D and 2D Human Representations](https://mlsanity.com/paper/1701.02468/) (2017)
- [AGORA: Avatars in Geography Optimized for Regression Analysis](https://mlsanity.com/paper/2104.14643/) (2021)
- [Neural Body Fitting: Unifying Deep Learning and Model-Based Human Pose and Shape Estimation](https://mlsanity.com/paper/1808.05942/) (2018)
- [Monocular Total Capture: Posing Face, Body, and Hands in the Wild](https://mlsanity.com/paper/1812.01598/) (2018)
- [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018)
- [Compositional Human Pose Regression](https://mlsanity.com/paper/1704.00159/) (2017)
- [Exemplar Fine-Tuning for 3D Human Model Fitting Towards In-the-Wild 3D Human Pose Estimation](https://mlsanity.com/paper/2004.03686/) (2020)
- [Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction](https://mlsanity.com/paper/2006.08072/) (2020)
- [Ordinal Depth Supervision for 3D Human Pose Estimation](https://mlsanity.com/paper/1805.04095/) (2018)
- [DenseRaC: Joint 3D Pose and Shape Estimation by Dense Render-and-Compare](https://mlsanity.com/paper/1910.00116/) (2019)

## Built on by (most cited first, 30 of 39)

- [Capturing and Inferring Dense Full-Body Human-Scene Contact](https://mlsanity.com/paper/2206.09553/) (2022)
- [PyMAF-X: Towards Well-aligned Full-body Model Regression from Monocular Images](https://mlsanity.com/paper/2207.06400/) (2022)
- [Putting People in their Place: Monocular Regression of 3D People in Depth](https://mlsanity.com/paper/2112.08274/) (2021)
- [Recovering 3D Human Mesh from Monocular Images: A Survey](https://mlsanity.com/paper/2203.01923/) (2022)
- [Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer](https://mlsanity.com/paper/2204.08680/) (2022)
- [TokenHMR: Advancing Human Mesh Recovery with a Tokenized Pose Representation](https://mlsanity.com/paper/2404.16752/) (2024)
- [Cross-Attention of Disentangled Modalities for 3D Human Mesh Recovery with Transformers](https://mlsanity.com/paper/2207.13820/) (2022)
- [EgoHumans: An Egocentric 3D Multi-Human Benchmark](https://mlsanity.com/paper/2305.16487/) (2023)
- [Occluded Human Mesh Recovery](https://mlsanity.com/paper/2203.13349/) (2022)
- [Accurate 3D Body Shape Regression using Metric and Semantic Attributes](https://mlsanity.com/paper/2206.07036/) (2022)
- [TORE: Token Reduction for Efficient Human Mesh Recovery with Transformer](https://mlsanity.com/paper/2211.10705/) (2022)
- [POTTER: Pooling Attention Transformer for Efficient Human Mesh Recovery](https://mlsanity.com/paper/2303.13357/) (2023)
- [Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions](https://mlsanity.com/paper/2410.20294/) (2024)
- [Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms](https://mlsanity.com/paper/2209.10529/) (2022)
- [PICO: Reconstructing 3D People In Contact with Objects](https://mlsanity.com/paper/2504.17695/) (2025)
- [A Lightweight Graph Transformer Network for Human Mesh Reconstruction from 2D Human Pose](https://mlsanity.com/paper/2111.12696/) (2021)
- [POCO: 3D Pose and Shape Estimation with Confidence](https://mlsanity.com/paper/2308.12965/) (2023)
- [InteractVLM: 3D Interaction Reasoning from 2D Foundational Models](https://mlsanity.com/paper/2504.05303/) (2025)
- [Disco4D: Disentangled 4D Human Generation and Animation from a Single Image](https://mlsanity.com/paper/2409.17280/) (2024)
- [Learning Visibility for Robust Dense Human Body Estimation](https://mlsanity.com/paper/2208.10652/) (2022)
- [VQ-HPS: Human Pose and Shape Estimation in a Vector-Quantized Latent Space](https://mlsanity.com/paper/2312.08291/) (2023)
- [JOTR: 3D Joint Contrastive Learning with Transformers for Occluded Human Mesh Recovery](https://mlsanity.com/paper/2307.16377/) (2023)
- [AWOL: Analysis WithOut synthesis using Language](https://mlsanity.com/paper/2404.03042/) (2024)
- [FeatER: An Efficient Network for Human Reconstruction via Feature Map-Based TransformER](https://mlsanity.com/paper/2205.15448/) (2022)
- [PointHPS: Cascaded 3D Human Pose and Shape Estimation from Point Clouds](https://mlsanity.com/paper/2308.14492/) (2023)
- [SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation](https://mlsanity.com/paper/2404.15276/) (2024)
- [Primitive-based 3D Human-Object Interaction Modelling and Programming](https://mlsanity.com/paper/2312.10714/) (2023)
- [Towards Robust and Expressive Whole-body Human Pose and Shape Estimation](https://mlsanity.com/paper/2312.08730/) (2023)
- [HumMUSS: Human Motion Understanding using State Space Models](https://mlsanity.com/paper/2404.10880/) (2024)
- [ShapeBoost: Boosting Human Shape Estimation with Part-Based Parameterization and Clothing-Preserving Augmentation](https://mlsanity.com/paper/2403.01345/) (2024)

## Abstract (arXiv)

Learning to regress 3D human body shape and pose (e.g.~SMPL parameters) from monocular images typically exploits losses on 2D keypoints, silhouettes, and/or part-segmentation when 3D training data is not available. Such losses, however, are limited because 2D keypoints do not supervise body shape and segmentations of people in clothing do not match projected minimally-clothed SMPL shapes. To exploit richer image information about clothed people, we introduce higher-level semantic information about clothing to penalize clothed and non-clothed regions of the image differently. To do so, we train a body regressor using a novel Differentiable Semantic Rendering - DSR loss. For Minimally-Clothed regions, we define the DSR-MC loss, which encourages a tight match between a rendered SMPL body and the minimally-clothed regions of the image. For clothed regions, we define the DSR-C loss to encourage the rendered SMPL body to be inside the clothing mask. To ensure end-to-end differentiable training, we learn a semantic clothing prior for SMPL vertices from thousands of clothed human scans. We perform extensive qualitative and quantitative experiments to evaluate the role of clothing semantics on the accuracy of 3D human pose and shape estimation. We outperform all previous state-of-the-art methods on 3DPW and Human3.6M and obtain on par results on MPI-INF-3DHP. Code and trained models are available for research at https://dsr.is.tue.mpg.de/.